AI Factory in Hybrid Manager

AI Factory in Hybrid Manager#

  • /purl/hm/ai-factory navigation:

  • “#Getting started”

  • getting-started

  • architecture

  • sovereign-ai-on-hm

  • use-cases-and-personas

  • faq

  • gpu-recommended

  • quickstart

  • “#Manual”

  • how-to-enable-ai-factory

  • gen-ai

  • models

  • “#Setup”

  • prerequisites

  • deploy-with-hm-ui

  • advanced-deployment

  • “#How-to (Use Models)”

  • using-models-in-model-clusters

  • “#How-to (Use Gen AI builder)”

  • using-models-in-gen-ai-builder

  • “#Operate & Observe”

  • observability

  • troubleshooting The AI Factory workload in Hybrid Manager brings scalable AI, machine learning, and Gen AI capabilities to your Hybrid Manager platform. It enables you to operationalize AI across your Hybrid Manager–managed clusters and data — with deep integration across Postgres, vector search, model serving, and AI assistants.

With AI Factory in Hybrid Manager, you can:

  • Deploy Gen AI assistants and agents for internal or external-facing use

  • Serve AI models at scale with integrated KServe-powered inferencing and GPU acceleration

  • Create Knowledge Bases and perform Retrieval-Augmented Generation (RAG) with vector search

  • Manage your model library and deploy trusted models under Hybrid Manager governance

  • Integrate AI features directly into your applications and data pipelines

Hub quick links: AI Factory Hub — Gen AI Builder on Hybrid Manager — Model Serving

For in-depth architecture and core concepts, see the AI Factory Hub .

Example AI solutions you can build#

AI Factory in Hybrid Manager enables solutions across many domains:

  • Enterprise search and knowledge assistants Build RAG-based assistants that integrate with corporate documents, databases, and intranet content.

  • Customer support chatbots Deploy assistants powered by your own data and domain-specific models, combining conversational AI with Knowledge Bases.

  • AI-driven data apps Expose AI-powered endpoints for apps — semantic search, recommendations, similarity search, or natural language querying.

  • Operational AI for internal tools Build AI agents and tools to assist with DevOps, customer success, HR automation, sales enablement, and more.

  • Domain-specific model serving Serve proprietary or fine-tuned models (LLMs, embedding models, ranking models) as scalable inference services within your Hybrid Manager cluster.

You can start small — with a single assistant or model endpoint — and scale to full AI-powered applications using the AI Factory architecture.

Learning paths#

Follow structured learning paths to master AI Factory in Hybrid Manager:

  • :ref;`AI Factory 101 <Postgres clusters>` — Introductory concepts and usage

  • :ref;`AI Factory 201 <Postgres clusters>` — Building and managing Gen AI and AI Factory workloads

  • :ref;`AI Factory 301 <Postgres clusters>` — Advanced integration, scaling, governance, and optimization

Use cases and solutions#

We provide detailed guidance and patterns to help you build solutions with AI Factory:

  • :ref;`Common workloads and use cases <Common workloads and use cases>` — Proven patterns for AI Factory–powered applications

  • :ref;`Industry Solutions <Postgres clusters>` — Industry-specific examples and best practices

AI Factory in Hybrid Manager workloads#

Hybrid Manager supports a full set of AI Factory capabilities, tightly integrated into its control plane:

Gen AI workloads#

  • :ref;`Gen AI in Hybrid Manager <Gen AI Builder on Hybrid Manager>` — Gen AI capabilities in Hybrid Manager

  • :ref;`Agent Studio & Builder (consolidated) <Gen AI Builder on Hybrid Manager>` — Create assistants, tools, structures, rulesets; manage Knowledge Bases

Model management and serving#

  • :ref;`Model Library Architecture <Model Library Architecture>` — Manage and govern your model assets

  • :ref;`Model Serving <Model Serving>` — Deploy and scale model inference services on Kubernetes

  • :ref;`GPU resource management <Postgres clusters>` — Configure and allocate GPU capacity for serving

Vector Engine#

  • :ref;`Vector Engine <Vector Engine>` — Integrated vector search and similarity capabilities with Postgres

Hybrid Manager learn content#

In addition to AI Factory content in the hub, Hybrid Manager provides additional Learn content for Hybrid Manager–specific usage:

  • :ref;`Concepts and architecture <Concepts and architecture>`

  • :ref;`How-To Guides <Gen AI Builder on Hybrid Manager>`

  • :ref;`Learning paths <Learning paths>`

How AI Factory fits within Hybrid Manager#

Hybrid Manager is the control plane for your databases, analytics, and AI workloads. AI Factory complements other HM capabilities:

  • Databases: Provision and manage Postgres clusters; AI Factory connects to these for vector search, RAG, and application endpoints.

  • Analytics: Offload data to Iceberg/Delta and query via SQL; AI Factory’s Pipelines and Vector Engine integrate with these datasets for retrieval.

  • Operations: Use HM observability and governance to monitor Gen AI, Pipelines, and model serving alongside databases and analytics.

Prerequisites for AI Factory in HM:

  • A Hybrid Manager project with AI Factory enabled and required entitlements for Gen AI, Pipelines, Vector Engine, and Model Serving.

  • Access to GPU resources where needed for serving. See GPU resource management .

Get started#

To begin building with AI Factory in Hybrid Manager:

AI Factory in Hybrid Manager gives you a scalable, secure platform to operationalize AI across your hybrid data estate.

Contents